© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7200
    Prev
    Next
    INDEX
    Explanations

    descriptions of wrestling matches and athletic competitions, often with scores

    oai_token-act-pair · gemini-2.0-flash

    Seasons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.69
    MessageTagHelper
    -0.65
     Roskov
    -0.62
    клопе
    -0.58
    
    -0.56
     resourceCulture
    -0.55
     berken
    -0.53
    kloped
    -0.52
    lossians
    -0.52
     esternos
    -0.51
    POSITIVE LOGITS
     season
    0.71
     seasons
    0.59
    FXML
    0.59
    Season
    0.56
    season
    0.54
    Ligações
    0.53
     Krakowie
    0.52
     SEASON
    0.52
     Season
    0.52
     stagione
    0.51
    Activations Density 4.290%

    No Known Activations